Create app.py

app.py

@@ -0,0 +1,59 @@
+import gradio as gr
+from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline
+
+# --- Load Model ---
+MODEL_PATH = "./tinyllama-jobskills-final_update_4"  # Model files are in the repo root
+
+tokenizer = AutoTokenizer.from_pretrained(MODEL_PATH)
+model = AutoModelForCausalLM.from_pretrained(
+    MODEL_PATH,
+    trust_remote_code=True,
+    device_map="auto"
+)
+
+pipe = pipeline(
+    "text-generation",
+    model=model,
+    tokenizer=tokenizer,
+    device_map="auto"
+)
+
+# --- Define Chat Function ---
+def chat_fn(message, history):
+    history_text = ""
+    for user, bot in history:
+        history_text += f"User: {user}\nAssistant: {bot}\n"
+    history_text += f"User: {message}\nAssistant:"
+
+    # generate response
+    response = pipe(
+        history_text,
+        max_new_tokens=256,
+        do_sample=True,
+        temperature=0.7,
+        top_p=0.9
+    )[0]["generated_text"]
+
+    # extract assistant reply
+    reply = response.split("Assistant:")[-1].strip()
+    return reply
+
+# --- Gradio UI ---
+with gr.Blocks() as demo:
+    gr.Markdown("## 🚀 Chat with My Custom Model")
+
+    chatbot = gr.Chatbot()
+    msg = gr.Textbox(label="Type your message")
+    clear = gr.Button("Clear")
+
+    def user_fn(user_message, chat_history):
+        bot_message = chat_fn(user_message, chat_history)
+        chat_history.append((user_message, bot_message))
+        return "", chat_history
+
+    msg.submit(user_fn, [msg, chatbot], [msg, chatbot])
+    clear.click(lambda: None, None, chatbot, queue=False)
+
+# --- Launch ---
+if __name__ == "__main__":
+    demo.launch()